SubspaceNet: Deep Learning-Aided Subspace Methods for DoA Estimation

TL;DR

SubspaceNet introduces a deep learning-based approach to improve subspace methods for DoA estimation, enabling accurate source localization under challenging conditions like coherence, wideband signals, and array mismatches.

Contribution

It develops a neural network that learns to estimate the autocorrelation matrix, enhancing traditional subspace methods without requiring ground-truth autocorrelation data.

Findings

Improves DoA estimation with coherent sources and wideband signals.

Enhances robustness to low SNR and array mismatches.

Maintains interpretability of classical subspace methods.

Abstract

Direction of arrival (DoA) estimation is a fundamental task in array processing. A popular family of DoA estimation algorithms are subspace methods, which operate by dividing the measurements into distinct signal and noise subspaces. Subspace methods, such as Multiple Signal Classification (MUSIC) and Root-MUSIC, rely on several restrictive assumptions, including narrowband non-coherent sources and fully calibrated arrays, and their performance is considerably degraded when these do not hold. In this work we propose SubspaceNet; a data-driven DoA estimator which learns how to divide the observations into distinguishable subspaces. This is achieved by utilizing a dedicated deep neural network to learn the empirical autocorrelation of the input, by training it as part of the Root-MUSIC method, leveraging the inherent differentiability of this specific DoA estimator, while removing the need to provide a ground-truth decomposable autocorrelation matrix. Once trained, the resulting SubspaceNet serves as a universal surrogate covariance estimator that can be applied in combination with any subspace-based DoA estimation method, allowing its successful application in challenging setups. SubspaceNet is shown to enable various DoA estimation algorithms to cope with coherent sources, wideband signals, low SNR, array mismatches, and limited snapshots, while preserving the interpretability and the suitability of classic subspace methods.